Skill 与 AgentSKILLS & AGENTS· MCP-SERVER
1llu50ry/Decompile
一个MCP服务器,让AI助手能直接分析二进制文件、反编译和逆向工程。An MCP server for reverse engineering, with 6,000+ skill documents and 230+ tools for AI assistants.
根据公开文档整理,未运行实测;费用以项目官网为准。Based on public documentation, without runtime testing. Check the project site for pricing.
能力CAPABILITIES
拆开游戏或软件,看懂它的内部逻辑
把反汇编结果直接发给 Claude 等程序分析
一键安装 Ghidra、radare2、Frida 等反编译工具
用一条命令分析二进制文件并输出结构化结果
在 IDA、Binary Ninja、Cheat Engine 里直接调用这个工具
Analyze PE, ELF, Mach-O, and other binary formats.
Decompile code using Ghidra, IDA, or Binary Ninja.
Inspect runtime behavior with Frida and Cheat Engine.
Search 6,000+ documented reverse engineering techniques.
Generate structured findings from any binary file.
上手GET STARTED
curl -fsSL https://raw.githubusercontent.com/1llu50ry/Decompile/main/install.sh | sh选择与你的环境对应的方式。命令来自项目文档,未运行实测。Choose the option for your environment. Commands come from project documentation and have not been run-tested.
使用限制LIMITATIONS
以下要求与风险来自文档静态检查,未执行项目代码;扫描没有命中,不代表使用安全。Risk here is evidence, not an alarm. These findings come from static scanning of the docs; we never execute a project’s code.
限制LIMITS
存在风险Risk found
静态扫描STATIC SCAN
01执行远程脚本Runs a remote scriptreadme
curl -fsSL https://raw.githubusercontent.com/1llu50ry/Decompile/main/install.sh | sh
静态扫描发现高风险项:安装脚本通过 curl | sh 执行远程代码,存在中间人攻击或脚本篡改风险。仅核验官方页面,未审计服务端代码;数据处理和费用以官网为准。The curl pipe installation method downloads and runs a remote script, which is a security risk. Consider using the npx method or reviewing the script first.
项目动态PROJECT ACTIVITY
首次发现FIRST SEEN
23 OCT 202623 OCT 2026
增长GROWTH
+143.8%+143.8%
242 → 590 stars · 5 个快照242 → 590 stars · 5 snapshots
状态STATUS
持续活跃Active
质量 A-Quality A-
近 7 天有 13 次提交,项目仍在活跃更新。Integrates 60+ reverse engineering backends into one MCP server.
依赖:Dependencies:@modelcontextprotocol/sdk, acorn
{
"agents": [
{
"agent": "claude-code",
"evidence": "tree: .claude-plugin/"
},
{
"agent": "claude-desktop",
"evidence": "readme: …| | `re_mcp_config` | Emit a Claude Desktop / Claude Code / Cursor / Code…"
},
{
"agent": "cursor",
"evidence": "readme: …## Connect to Cursor Add to `.cursor/mcp.json`: ```json { \"mcpServers\": {…"
},
{
"agent": "windsurf",
"evidence": "readme: …laude Code / Cursor / Codex / Windsurf / Gemini and returns structur…"
},
{
"agent": "cline",
"evidence": "readme: …DeepSeek Harness, LM Studio, Cline in every host, Copilot CLI, G…"
},
{
"agent": "gemini-cli",
"evidence": "readme: …rsor, VS Code, Zed, Windsurf, Gemini CLI, Grok Build, Qwen Code, Kimi,…"
},
{
"agent": "vscode",
"evidence": "readme: …ode / Desktop, Codex, Cursor, VS Code, Zed, Windsurf, Gemini CLI, G…"
}
],
"apiKey": null,
"docker": null,
"taxonomy": {
"scores": {
"design": 0,
"ai-tools": 0,
"dev-tools": 2,
"indie-web": 0,
"skill-agent": 6,
"productivity": 0
},
"primary": "skill-agent",
"secondary": "mcp-server"
},
"localRuntime": "Code, Kimi, DeepSeek Harness, LM Studio, Cline in every host, Copilot CLI, Goos",
"skillMdTotal": 1,
"skillMdErrors": [],
"treeTruncated": false,
"categoryScores": {
"data": 3,
"agent": 1,
"media": 0,
"design": 0,
"browser": 0,
"devtool": 2,
"security": 1,
"marketing": 0,
"productivity": 0
},
"classification": [
{
"signal": "1 SKILL.md with name + description",
"weight": 0.95
},
{
"signal": "package.json depends on @modelcontextprotocol/sdk + MCP framing",
"weight": 0.8
},
{
"signal": "README describes a Claude / Agent Skill",
"weight": 0.7
},
{
"signal": "Claude Code plugin manifest",
"weight": 0.7
},
{
"signal": "README ships an mcpServers config for this server",
"weight": 0.7
},
{
"signal": "MCP topic + README",
"weight": 0.6
},
{
"signal": "description mentions AI",
"weight": 0.2
}
],
"scannedSources": [
"readme",
".claude-plugin/skills/workflow/SKILL.md"
],
"skillMdFetched": 1
}